Motion segmentation in Moving Camera Videos using Velocity Guided Optical Flow Normalization

Adinugroho, Sigit; Gofuku, Akio

doi:10.1145/3606283.3606284

Cited by 1 publication

(2 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We note that computing optical flow when either the observer is moving (and others are standing still), or when the observer halts (and others are moving) is relatively easy [ 35 , 96 ]. However, for the purposes of employing the model we present here, neither simplified variant would appear sufficient, as agents move while observing.…”

Section: Discussionmentioning

confidence: 99%

“…One of the most difficult challenges to the use of optical flow in crowded environments, even ignoring the issue of occlusions, is that it is difficult to compute when the agent's social environment is moving independently of its own movement. In other words, distinguishing the optical flow of observed agents that are moving in the vicinity of the observer, while the observer itself is moving, is computationally difficult, prone to errors, and sometimes impossible (this challenge also arises for SfM processes, discussed above) [35,[94][95][96][97].…”

Section: Reliable Velocity Estimatesmentioning

confidence: 99%

See 1 more Smart Citation

Vision-based collective motion: A locust-inspired reductionist model

Krongauz,

Ayali,

Kaminka

2024

PLoS Comput Biol

View full text Add to dashboard Cite

Naturally occurring collective motion is a fascinating phenomenon in which swarming individuals aggregate and coordinate their motion. Many theoretical models of swarming assume idealized, perfect perceptual capabilities, and ignore the underlying perception processes, particularly for agents relying on visual perception. Specifically, biological vision in many swarming animals, such as locusts, utilizes monocular non-stereoscopic vision, which prevents perfect acquisition of distances and velocities. Moreover, swarming peers can visually occlude each other, further introducing estimation errors. In this study, we explore necessary conditions for the emergence of ordered collective motion under restricted conditions, using non-stereoscopic, monocular vision. We present a model of vision-based collective motion for locust-like agents: elongated shape, omni-directional visual sensor parallel to the horizontal plane, and lacking stereoscopic depth perception. The model addresses (i) the non-stereoscopic estimation of distance and velocity, (ii) the presence of occlusions in the visual field. We consider and compare three strategies that an agent may use to interpret partially-occluded visual information at the cost of the computational complexity required for the visual perception processes. Computer-simulated experiments conducted in various geometrical environments (toroidal, corridor, and ring-shaped arenas) demonstrate that the models can result in an ordered or near-ordered state. At the same time, they differ in the rate at which order is achieved. Moreover, the results are sensitive to the elongation of the agents. Experiments in geometrically constrained environments reveal differences between the models and elucidate possible tradeoffs in using them to control swarming agents. These suggest avenues for further study in biology and robotics.

show abstract

Section: Discussionmentioning

confidence: 99%